Segmented Microcalcifications Research Articles

An Automatic Detection and Localization of Mammographic Microcalcifications ROI with Multi-Scale Features Using the Radiomics Analysis Approach.

Simple SummaryBreast cancer is one of the foremost causes of cancer-related mortality in women. It is curable and controllable only if detected early. Microcalcifications in breast tissue are essential predictors for radiologists to detect early-stage breast cancer. This study proposes a method for detecting and classifying microcalcifications in mammogram images to predict breast lesions, using machine learning coupled with an interpretable radiomics approach. The method was evaluated using a publicly accessible dataset, which may aid radiologists and clinicians in identifying breast cancer in their regular clinical practices. This study contributes to the field of predictive modeling in healthcare.Microcalcifications in breast tissue can be an early sign of breast cancer, and play a crucial role in breast cancer screening. This study proposes a radiomics approach based on advanced machine learning algorithms for diagnosing pathological microcalcifications in mammogram images and provides radiologists with a valuable decision support system (in regard to diagnosing patients). An adaptive enhancement method based on the contourlet transform is proposed to enhance microcalcifications and effectively suppress background and noise. Textural and statistical features are extracted from each wavelet layer’s high-frequency coefficients to detect microcalcification regions. The top-hat morphological operator and wavelet transform segment microcalcifications, implying their exact locations. Finally, the proposed radiomic fusion algorithm is employed to classify the selected features into benign and malignant. The proposed model’s diagnostic performance was evaluated on the MIAS dataset and compared with traditional machine learning models, such as the support vector machine, K-nearest neighbor, and random forest, using different evaluation parameters. Our proposed approach outperformed existing models in diagnosing microcalcification by achieving an 0.90 area under the curve, 0.98 sensitivity, and 0.98 accuracy. The experimental findings concur with expert observations, indicating that the proposed approach is most effective and practical for early diagnosing breast microcalcifications, substantially improving the work efficiency of physicians.

Computational FEM Model and Phantom Validation of Microwave Ablation for Segmental Microcalcifications in Breasts Using a Coaxial Double-Slot Antenna.

Introduction Cancer is the second leading cause of death worldwide. Breast cancer is the second most common cause of cancer-related mortality, accounting for 11.6% of the total number of deaths. The main treatments for this disease are surgical removal of the tumor, radiotherapy, and chemotherapy. Recently, different minimally invasive technologies have been applied (e.g., emission of electromagnetic waves, thermal and chemical means) to overcome the important side effects of these treatment modalities. The objective of this study was to develop and evaluate a predictive computational model of microwave ablation. Materials and Methods The predictive computational model of microwave ablation was constructed by means of a dual-slot coaxial antenna. The model was compared with an experiment performed using a breast phantom, which emulates the dielectric properties of breast tissue with segmental microcalcifications. The standing wave ratio (SWR) was obtained for both methods to make a comparison and determine the feasibility of applying electromagnetic ablation to premalignant lesions in breasts. Specifically, for the analysis of segmental microcalcifications, a breast phantom with segmental microcalcifications was developed and two computational models were performed under the same conditions (except for blood perfusion, which was excluded in one of the models). Results The SWR was obtained by triplicate experiments in the phantom, and the measurements had a difference of 0.191 between the minimum and maximum SWR values, implying a change of power reflection of 0.8%. The average of the three measurements was compared with the simulation that did not consider blood perfusion. The comparison yielded a change of 0.104, representing a 0.2% change in power reflection. Discussion. Both experimentation in phantom and simulations demonstrated that ablation therapy can be performed using this antenna. However, an additional optimization procedure is warranted to increase the efficiency of the antenna.

Abstract P2-01-02: Do decreased breast microcalcifications after neoadjuvant chemotherapy predict pathological complete response?

Abstract Background: Clinical response evaluation by image examination after neoadjuvant chemotherapy for breast cancer is important for determining drug response and progression. Mammography is less correlated with pathological response assessment than magnetic resonance imaging or ultrasonography particularly because mammographic calcifications can increase or decrease in response to neoadjuvant chemotherapy. A conventional theory of breast microcalcifications is that they are likely to paradoxically change with neoadjuvant chemotherapy. Traditionally, microcalcifications have been said to occur due to necrosis. If conventional theory is correct, the increase in necrotic cells would increase microcalcifications in response to neoadjuvant chemotherapy. However, decreased microcalcifications were found as a clinical response to neoadjuvant chemotherapy in many cases. To increase the diagnostic ability of mammography after neoadjuvant chemotherapy, it is important to clarify the cases in which microcalcifications can be reduced by anticancer agents. The present study clarified characteristics of breast cancer cases with decreased microcalcifications after neoadjuvant. Methods: Consecutive patients who received neoadjuvant chemotherapy for breast cancer at our hospital from January 2013 to June 2017 were retrospectively reviewed. Characteristics of cases with microcalcifications before neoadjuvant chemotherapy and those showing a reduction after were examined. Stromal tumor-infiltrating lymphocytes were evaluated in the biopsy. before neoadjuvant chemotherapy based on the protocol of the International TILs Working Group 2014. Pathological complete response was also explored in cases exhibiting a decrease in microcalcifications by neoadjuvant chemotherapy. In addition, sensitivity, specificity, and likelihood ratios were calculated for pCR assessment in patients with segmental microcalcifications, pleomorphic/linear microcalcifications, and microcalcifications without mammographic mass. Results: A total of 184 breast cancer cases, including 8 with synchronous bilateral breast cancer, received neoadjuvant chemotherapy at our hospital. Of them, 114 cases were excluded due to unavailable mammograms at our institute before or after neoadjuvant chemotherapy. Seventy breast cancer cases were included; 37 had no malignant microcalcifications before neoadjuvant chemotherapy and 33 did. Breast cancer with microcalcifications was significantly more positive for human epidermal growth factor receptor 2 than those without microcalcifications (48% versus 22%, P = 0.018). Only 6 out of 33 cases with microcalcifications before neoadjuvant chemotherapy showed a decrease after treatment. These cases tended to have high stromal tumor-infiltrating lymphocytes (50% versus 17%), segmental microcalcifications (66% versus 33%), and pleomorphic/linear microcalcifications (83% versus 37%). The sensitivity of each group, compared with total cases of microcalcifications after neoadjuvant chemotherapy, tended to increase, although no significant difference was observed (sensitivity; patients with segmental microcalcifications, 42.9%; patients with pleomorphic/linear microcalcifications, 57.1%; and patients with microcalcifications but without mass, 50.0%). Conclusion: These results suggest that neoadjuvant chemotherapy is able to decrease malignant calcifications, particularly segmental and pleomorphic/linear microcalcifications and microcalcifications with high stromal tumor-infiltrating lymphocytes. By clarifying the mechanisms of formation and disappearance of microcalcifications, a consensus can be reached on whether microcalcifications apparent by mammography are useful for evaluating response to neoadjuvant chemotherapy. Citation Format: Atsushi Fushimi, Rei Kudo, Hiroshi Takeyama. Do decreased breast microcalcifications after neoadjuvant chemotherapy predict pathological complete response? [abstract]. In: Proceedings of the 2019 San Antonio Breast Cancer Symposium; 2019 Dec 10-14; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2020;80(4 Suppl):Abstract nr P2-01-02.

Do Decreased Breast Microcalcifications After Neoadjuvant Chemotherapy Predict Pathologic Complete Response?

BackgroundClinical response evaluation by image examination after neoadjuvant chemotherapy for breast cancer is important for determining drug response and progression. Mammography is less correlated with pathologic response assessment than magnetic resonance imaging or ultrasonography. The present study clarified characteristics of breast cancer patients with decreased microcalcifications after neoadjuvant chemotherapy to increase the accuracy of mammographic assessment. Patients and MethodsConsecutive patients who received neoadjuvant chemotherapy for breast cancer at our hospital from January 2013 to June 2017 were retrospectively reviewed. Characteristics of cases of microcalcifications before neoadjuvant chemotherapy and those showing a reduction after were examined. Stromal tumor-infiltrating lymphocytes were evaluated in the biopsy. Pathologic complete response was also explored in patients exhibiting a decrease in microcalcifications by neoadjuvant chemotherapy. ResultsSeventy breast cancer cases were included; 37 had no malignant microcalcifications before neoadjuvant chemotherapy and 33 did. Breast cancer with microcalcifications was significantly more positive for human epidermal growth factor receptor 2 than those without microcalcifications (48% vs. 22%, P = .018). Only 6 of 33 patients with microcalcifications before neoadjuvant chemotherapy showed a decrease after treatment. These patients tended to have high stromal tumor-infiltrating lymphocytes (50% vs. 17%), segmental microcalcifications (66% vs. 33%), and pleomorphic/linear microcalcifications (83% vs. 37%). ConclusionThese results suggest that neoadjuvant chemotherapy is able to decrease malignant calcifications, particularly segmental and pleomorphic/linear microcalcifications. By clarifying the mechanisms of formation and disappearance of microcalcifications, a consensus can be reached on whether microcalcifications apparent by mammography are useful for evaluating response to neoadjuvant chemotherapy.

Features of Microcalcifications on Screening Mammography in Young Women

Background:There is no decrease in the number of breast cancer deaths if screening mammography is performed in women aged <40 years. However, NCCN guidelines recommend screening mammography in young women at risk of hereditary breast cancer. Therefore, more accurate screening mammography for young women is needed.Objective:To evaluate the features of screening mammographic findings, particularly microcalcifications, in women aged <50 years to increase the positive predictive value of screening mammography in young women.Methods:We retrospectively reviewed the data of consecutive women who underwent opportunistic and organized breast cancer screening at the Sakuragaoka Hospital (Shizuoka, Japan) between April 2013 and March 2015. We compared the mammographic findings and features of microcalcifications between women aged <40 and 40–49 years and those aged 50–74 years.Results:The study included 3645 women. Of these 3645 women, 415 (11.4%) were aged <40 years, 1219 (33.4%) were aged 40–49 years, and 2011 (55.2%) were aged 50–74 years. Women aged <50 years were more likely to be recalled for microcalcifications than those aged 50–74 years (<40 years, 4.8%; 40–49 years, 4.3%; 50–74 years, 3.3%). Young women were more likely to be recalled for small round and segmental microcalcifications [<40 years, odds ratio (OR): 1.799 (95% CI: 0.751–2.846); 40–49 years, OR: 1.394 (95% CI: 0.714–2.074)] and less likely to be recalled for small round and grouped microcalcifications [<40 years, OR: 0.603 (95% CI: 0.181–1.025); 40–49 years, OR: 0.961 (95% CI: 0.496–1.428)] compared with women aged 50–74 years.Conclusions:On screening mammography, women aged <50 years had a higher tendency to be recalled for microcalcifications, particularly small round and segmental microcalcifications. False-positive results may be reduced by reflecting the characteristics of microcalcification findings among young women without breast cancer in the future.

Evaluating geodesic active contours in microcalcifications segmentation on mammograms

Breast cancer is the most commonly occurring type of cancer among women, and it is the major cause of female cancer-related deaths worldwide. Its incidence is increasing in developed as well as developing countries. Efficient strategies to reduce the high death rates due to breast cancer include early detection and tumor removal in the initial stages of the disease. Clinical and mammographic examinations are considered the best methods for detecting the early signs of breast cancer; however, these techniques are highly dependent on breast characteristics, equipment quality, and physician experience. Computer-aided diagnosis (CADx) systems have been developed to improve the accuracy of mammographic diagnosis; usually such systems may involve three steps: (i) segmentation; (ii) parameter extraction and selection of the segmented lesions and (iii) lesions classification. Literature considers the first step as the most important of them, as it has a direct impact on the lesions characteristics that will be used in the further steps. In this study, the original contribution is a microcalcification segmentation method based on the geodesic active contours (GAC) technique associated with anisotropic texture filtering as well as the radiologists’ knowledge. Radiologists actively participate on the final step of the method, selecting the final segmentation that allows elaborating an adequate diagnosis hypothesis with the segmented microcalcifications presented in a region of interest (ROI). The proposed method was assessed by employing 1000 ROIs extracted from images of the Digital Database for Screening Mammography (DDSM). For the selected ROIs, the rate of adequately segmented microcalcifications to establish a diagnosis hypothesis was at least 86.9%, according to the radiologists. The quantitative test, based on the area overlap measure (AOM), yielded a mean of 0.52±0.20 for the segmented images, when all 2136 segmented microcalcifications were considered. Moreover, a statistical difference was observed between the AOM values for large and small microcalcifications. The proposed method had better or similar performance as compared to literature for microcalcifications with maximum diameters larger than 460μm. For smaller microcalcifications the performance was limited.

Study on Microcalcification Detection Using Wavelet Singularity

A microcalcification detection method based on wavelet singularity was presented because of microcalcification singularity characteristic. Firstly, the source image is decomposed in multi-scales wavelet coefficients. Secondly, coefficients in low-pass band are removed and coefficients in high-pass band are enhanced contrast by nonlinear method. Lastly, fisher discriminant was adopted in segment microcalcifications. Experiment results showed that wavelet basis with shorter support and lower regularity is more sensitive to noise, while wavelet basis with longer support, higher regularity and higher order vanishing moment could segment indistinct microcalcifications, but sometime could not segment small microcalcifications. The results also showed the detect effect DAUB4 wavelet is best and its detection ratio is about 96%.

Segmenting mammographic microcalcifications using a semi-automatic procedure based on Otsu s method and morphological filters

INTRODUCTION: Breast cancer has the second highest world's incidence rate, according to the Brazilian National Cancer Institute (INCa). Clinical examination and mammography are the best methods for early diagnosis. Computer-aided detection (CADe) and computer-aided diagnosis (CADx) systems are developed to improve mammographic diagnosis. Basically, CADx systems have three components: (i) segmentation, (ii) parameters extraction and selection, (iii) lesion classification. The first step for a CADx system is segmentation. METHODS: A microcalcification segmentation method is proposed, based on morphological operators, Otsu's Method and radiologists' knowledge. Pre-processing with top-hat operators improves contrast and reduces background noise. The Otsu's method automatically selects the best grey-level threshold to segment microcalcifications, obtaining binary images. Following, inferior reconstruction and morphological dilatation operators are applied to reconstruct lost structure details and fill small flaws in the segmented microcalcifications. Finally, the Canny edge detection is applied to identify microcalcifications contour candidates for each region-of-interest (ROI). Two experienced radiologists intervene in this semi-automatic method, firstly, selecting the ROI and, then, analyzing the segmentation result. The method was assessed in 1000 ROIs from 158 digital images (300 dpi, 8 bits). RESULTS: Considering the radiologists opinion, the rates of ROIs adequately segmented to establish a diagnosis hypothesis were 97.8% for one radiologist and 97.3% for the other. Using the Area Overlap Measure (AOM) and the 2136 microcalcifications delineated by an experienced radiologist as gold standards, the method achieved an average AOM of 0.64±0.14, being 0.56±0.09 for small microcalcifications and 0.66±0.13 for the large ones. Moreover, AOM was 0.64±0.13 for the benign and 0.64±0.14 for the malignant lesions with no statistical differences between them. CONCLUSION: Based on these findings, the proposed method could be used to develop a CADx system that could help early breast cancer detection.

Category assessment based on 3D volume data acquired by automated breast ultrasonography

To assess the validity of categorization of ultrasonographic findings using automated breast ultrasonography (US). Bilateral whole-breast US was performed using an automated breast volume scanner (ABVS) in 400 women. The 3D data were evaluated using the ABVS workstation, and final assessment categories were recorded based on the following criteria. Irregular-shaped masses with a spiculated margin or echogenic halo were defined as category 5. Solid masses with one of the three suspicious findings (no circumscribed margin, no parallel orientation, and microcalcifications) were defined as category 4a, and masses with two or more suspicious findings were defined as category 4b. For non-mass lesions, localized hypoechoic areas with one of the three suspicious findings (segmental distribution, ductal change, and microcalcifications) were defined as category 4a. Localized hypoechoic areas with two or three suspicious findings were defined as category 4b or 5, respectively. Malignancy was confirmed histologically in 57 women (invasive, n = 38; in situ, n = 19). The rate of malignant findings was 0.6% (1/168) in category 3, 12% (15/129) in category 4a, 53% (31/59) in category 4b and 100% (10/10) in category 5. Categorization of ultrasonographic findings using automated breast US are useful for predicting the likelihood of malignancy.

Can texture of tissue surrounding microcalcifications in mammography be used for breast cancer diagnosis?

This study investigates whether texture properties of the tissue surrounding microcalcifications (MCs) can contribute to breast cancer diagnosis. A case sample of 100 MC clusters (46 benign, 54 malignant) from 85 dense mammographic images included in the Digital Database for Screening Mammography, is analyzed. Regions of interest containing clusters are processed using wavelet-based enhancement and individual MCs are segmented by local thresholding. The segmented MCs are removed from original image data and the surrounding tissue area is subjected to texture analysis. The feasibility of four texture feature sets (first-order statistics, gray level co-occurrence matrices, gray level run length matrices and Laws’ texture energy measures) in discriminating malignant from benign tissue was investigated using a k-nearest neighbor classifier. Laws’ texture energy measures achieved the best classification accuracy 89% (sensitivity 90.74% and specificity 86.96%).

Segmentation of suspicious clustered microcalcifications in mammograms

We have developed a multistage computer-aided diagnosis (CAD) scheme for the automated segmentation of suspicious microcalcification clusters in digital mammograms. The scheme consisted of three main processing steps. First, the breast region was segmented and its high-frequency content was enhanced using unsharp masking. In the second step, individual microcalcifications were segmented using local histogram analysis on overlapping subimages. For this step, eight histogram features were extracted for each subimage and were used as input to a fuzzy rule-based classifier that identified subimages containing microcalcifications and assigned the appropriate thresholds to segment any microcalcifications within them. The final step clustered the segmented microcalcifications and extracted the following features for each cluster: the number of microcalcifications, the average distance between microcalcifications, and the average number of times pixels in the cluster were segmented in the second step. Fuzzy logic rules incorporating the cluster features were designed to remove nonsuspicious clusters, defined as those with typically benign characteristics. A database of 98 images, with 48 images containing one or more microcalcification clusters, provided training and testing sets to optimize the parameters and evaluate the CAD scheme, respectively. The results showed a true positive rate of 93.2% and an average of 0.73 false positive clusters per image. A comparison of our results with other reported segmentation results on the same database showed comparable sensitivity and at the same time an improved false positive rate. The performance of the CAD scheme is encouraging for its use as an automatic tool for efficient and accurate diagnosis of breast cancer.

A fuzzy logic based approach for semiological analysis of microcalcifications in mammographic images

We have developed a new algorithm for the characterization of microcalcification clusters. Fuzzy logic is well suited to represent and to manipulate data and knowledge at different levels of the algorithm. Our algorithm is built in 3 steps: Detection and segmentation of the individual microcalcifications, measurements on the segmented microcalcifications (shape, contrast, relative localization), use of these measurements as inputs of a learning system which concludes if the current case is malignant or not. We first describe some aspects of the fuzzy segmentation we have implemented. Then we explain how we build fuzzy measurements from the segmented objects and how these measurements are manipulated into the fuzzy decision tree we are using. Finally, we present the preliminary results we obtained with our test database.

A fuzzy logic based approach for semiological analysis of microcalcifications in mammographic images

We have developed a new algorithm for the characterization of microcalcification clusters. Fuzzy logic is well suited to represent and to manipulate data and knowledge at different levels of the algorithm. Our algorithm is built in 3 steps: Detection and segmentation of the individual microcalcifications, measurements on the segmented microcalcifications (shape, contrast, relative localization), use of these measurements as inputs of a learning system which concludes if the current case is malignant or not. We first describe some aspects of the fuzzy segmentation we have implemented. Then we explain how we build fuzzy measurements from the segmented objects and how these measurements are manipulated into the fuzzy decision tree we are using. Finally, we present the preliminary results we obtained with our test database. © 1997 John Wiley & Sons, Inc.

Segmentation and numerical analysis of microcalcifications on mammograms using mathematical morphology.

The top-hat and watershed algorithms of mathematical morphology have been applied to detect automatically and segment microcalcifications on mammograms digitized to a pixel resolution of 40 microns using a CCD camera. The database comprised 38 cases from the breast assessment clinic in Liverpool. For all cases, both craniocaudal (CC) and lateral oblique (LO) views were available. 19 cases were proven to be benign and 19 malignant based on cytology and histology. Malignant clusters contained more microcalcifications (14 malignant, 10 benign), occupied a larger area (37 mm2, 9 mm2) and had longer cluster perimeters than benign clusters (33.2 mm, 15.5 mm). Malignant microcalcifications exhibited a wider variety of shapes and were more heterogeneous in terms of image signal intensity than benign microcalcifications. Further mathematical morphology algorithms were applied to describe microcalcification shape in terms of the presence or absence of infoldings, elongation, narrow irregularities and wide irregularities. The three largest microcalcifications were selected for each case and, using a "leave-one-out" approach, each microcalcification was classified in respect of its five nearest neighbours as either malignant or benign. The area under the curve of a receiver operating characteristic (ROC) analysis of the proportion of the three microcalcifications which agreed with the true diagnosis increased from 0.73 (CC) and 0.63 (LO) to 0.79 when both views were considered. Next, each cluster in turn was ranked according to its agreement with the database as a whole over 21 features. An ROC analysis was performed to investigate the effect on sensitivity and specificity of the proportion of the nine nearest neighbours that agreed with the true classification. The largest area under the ROC curve was 0.84 produced by the four features of proportion of irregular microcalcifications, proportion of round microcalcifications, number of microcalcifications in the cluster and the interquartile range of microcalcification area. The shape of microcalcifications is confirmed as being of overriding importance in classifying cases as either malignant or benign. This observation motivates a further study enhanced by using magnified views digitized to a higher resolution by a laser scanner. This will enable the reliable assessment of the shape of a greater number of microcalcifications in each cluster, which is likely to increase further the discriminating power of the image analysis routines and lead to the development of an expert system for automatic mammographic screening.

Segmentation algorithms for detecting microcalcifications in mammograms.

The presence of microcalcification clusters in mammograms contributes evidence for the diagnosis of early stages of breast cancer. In many cases, microcalcifications are subtle and their detection can benefit from an automated system serving as a diagnostic aid. The potential contribution of such a system may become more significant as the number of mammograms screened increases to levels that challenge the capacity of radiology clinics. Many techniques for detecting microcalcifications start with a segmentation algorithm that indicates all candidate structures for the subsequent phases. Most algorithms used to segment microcalcifications have aspects that might raise operational difficulties, such as thresholds or windows that must be selected, or parametric models of the data. We present a new segmentation algorithm and compare it to two other algorithms: the multi-tolerance region growing algorithm that operates without the aspects mentioned above, and the active contour model that has not been applied previously to segment microcalcifications. The new algorithm operates without threshold or window selection, or parametric data models, and it is more than an order of magnitude faster than the other two.